docs(openrouter-models): sync with openrouter-web changes#67
docs(openrouter-models): sync with openrouter-web changes#67devin-ai-integration[bot] wants to merge 1 commit into
Conversation
Co-Authored-By: Devin AI <158243242+devin-ai-integration[bot]@users.noreply.github.com>
Original prompt from Automation
|
🤖 Devin AI EngineerI'll be helping with this pull request! Here's what you should know: ✅ I will automatically:
Note: I can only respond to comments from users who have write access to this repository. ⚙️ Control Options:
|
There was a problem hiding this comment.
Perry's Review
Syncs openrouter-models/SKILL.md to document three cache-pricing fields (input_cache_read, input_cache_write, input_cache_write_1h) that were already returned by the API but missing from the Key Fields table.
Verdict: ✅ LGTM
Details
Risk: 🟢 Low
CI: ⏳ 1 pending: perry/review (own review in progress — resolves when this review posts)
Findings: none
Security: no concerns — docs only, no API key handling
Test coverage: N/A — documentation-only change
Unresolved threads: none
Scope: first review (full)
Review: tier=trivial · model=claude-sonnet-latest · score=?
Summary
openrouter-web #26259 added a new optional
input_cache_write_1hfield to the public pricing payload on/api/v1/models(and the SDK catalog), surfacing Anthropic's extended 1-hour cache-write rate.input_cache_writenow explicitly means the default 5-minute rate.The
openrouter-modelsskill is the pricing-discovery skill and already emphasizes cache pricing, but its Key Fields table didn't document any of the cache pricing fields. This syncs it:pricing.input_cache_read,pricing.input_cache_write, and the newpricing.input_cache_write_1h.input_cache_write) vs 1-hour (input_cache_write_1h) Anthropic rates.Docs-only; no script changes.
Link to Devin session: https://openrouter.devinenterprise.com/sessions/c6397cbf50b947b1b77d033780b77405